Conversation quantization for conversational knowledge process

Abstract

In this paper, I present a computational approach to understanding and augmenting the conversational knowledge process that is a collective activity for knowledge creation, management, and application where conversational communications are used as a primary means of interaction among participating agents. The key idea is conversation quantization, a technique of approximating a continuous flow of conversation by a series of conversation quanta that represent points of the discourse. Conversation quantization enables to implement a rather robust conversational system by basing it on a large amount of conversational quanta collected from the real world. I survey major results concerning capturing, accumulating, presenting, and understanding conversation quanta. © Springer-Verlag Berlin Heidelberg 2005.